Triple

T9392027
Position Surface form Disambiguated ID Type / Status
Subject Stephen Boyd E226046 entity
Predicate spouse P13 FINISHED
Object Mariella di Sarzana
Mariella di Sarzana is the wife of American control theorist and Stanford professor Stephen Boyd.
 E796219 NE FINISHED

How this triple was built (4 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Mariella di Sarzana | Statement: [Stephen Boyd, spouse, Mariella di Sarzana]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Mariella di Sarzana
Context triple: [Stephen Boyd, spouse, Mariella di Sarzana]
  • A. Rosciano
    Rosciano is a small Italian municipality in the Abruzzo region, known for its rural landscape and traditional local agriculture.
  • B. Lesignano
    Lesignano is a locality or subdivision within the municipality of Serravalle in San Marino.
  • C. Segrate
    Segrate is a municipality in the Metropolitan City of Milan in northern Italy, known for its proximity to Milan and its role as a residential and commercial suburb.
  • D. Bellano
    Bellano is a picturesque town on the eastern shore of Lake Como in northern Italy, known for its lakeside promenade and the dramatic Orrido di Bellano gorge.
  • E. Impruneta
    Impruneta is a town in the Tuscany region of central Italy, situated in the hills just south of Florence and known for its terracotta production and scenic countryside.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Mariella di Sarzana
Triple: [Stephen Boyd, spouse, Mariella di Sarzana]
Generated description
Mariella di Sarzana is the wife of American control theorist and Stanford professor Stephen Boyd.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Mariella di Sarzana
Target entity description: Mariella di Sarzana is the wife of American control theorist and Stanford professor Stephen Boyd.
  • A. Rosciano
    Rosciano is a small Italian municipality in the Abruzzo region, known for its rural landscape and traditional local agriculture.
  • B. Lesignano
    Lesignano is a locality or subdivision within the municipality of Serravalle in San Marino.
  • C. Segrate
    Segrate is a municipality in the Metropolitan City of Milan in northern Italy, known for its proximity to Milan and its role as a residential and commercial suburb.
  • D. Bellano
    Bellano is a picturesque town on the eastern shore of Lake Como in northern Italy, known for its lakeside promenade and the dramatic Orrido di Bellano gorge.
  • E. Impruneta
    Impruneta is a town in the Tuscany region of central Italy, situated in the hills just south of Florence and known for its terracotta production and scenic countryside.
  • F. None of above. chosen

Provenance (5 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69ca842f7e3481908bf5bcf52e032dbd completed March 30, 2026, 2:09 p.m.
NER Named-entity recognition batch_69cd510eae0c8190b7c4ab487a366bb3 completed April 1, 2026, 5:08 p.m.
NED1 Entity disambiguation (via context triple) batch_69d1010169d88190a7267615a9196d4b completed April 4, 2026, 12:16 p.m.
NEDg Description generation batch_69d1024817f88190973d30bcbf0db228 completed April 4, 2026, 12:21 p.m.
NED2 Entity disambiguation (via description) batch_69d102b154f88190b13868ce5df59510 completed April 4, 2026, 12:23 p.m.
Created at: March 30, 2026, 7:45 p.m.